[cgl_discussion] [coyote@coyotegulch.com: 2.6.0 and Checkpointing]

Steven Dake sdake at mvista.com
Tue Nov 25 10:23:59 PST 2003


On Mon, 2003-11-24 at 19:28, Zhao, Forrest wrote:
> I have some thoughts about data check point service, just share them with you.
> 
> Generally speaking, there are two kinds of check-point services in terms of transparency.
> The first kind of check-point service is transparent to user/application.  CHPOX is just such kind of service. The major advantage of this kind is: there is no need to modify the application programs, the check pointing is done transparent to apps. The disadvantage of this kind is: it must save the whole process running context, so this can lead to inefficiency caused by saving unrelated, redundant data.

Another major disadvantage of process context checkpointing is loss of
control of the checkpointing process, which removes the ability to do
true live application upgrade in the field.  Without live application
upgrade of processes, any checkpointing solution is likely not to be
used.

Thanks
-steve

> The second kind of check-point service is not transparent to user/apps. 
> The data check point service defined by SAF(www.saforum.org)/AIS is such kind. The advantage of this kind is: the user can choose what specific data to check point, so reduce the volume of data to be saved. But the major disadvantage is: the developers have to insert the check-pointing API to apps in order to get data check-pointing service, so this kind of check-point service is not transparent to user/apps.
> 
> So there is a tradeoff between two kinds of services. But I'm wondering if the carrier companies are willing to modify their product quality software in order to get check-pointing service?
> 
> Thanks,
> Forrest
> 
> 
> -----Original Message-----
> From: cgl_discussion-bounces at lists.osdl.org [mailto:cgl_discussion-bounces at lists.osdl.org] On Behalf Of Rusty Lynch
> Sent: 2003年11月25日 5:38
> To: cgl_discussion at osdl.org
> Subject: [cgl_discussion] [coyote at coyotegulch.com: 2.6.0 and Checkpointing]
> 
> I thought this might be interesting to others in the CGL world.  I have 
> never ran across the chpox project before, and I'm not sure if this style
> of check-pointing is important to carrier environments, but it still looks
> interesting.
> 
>     --rustyl
> 
> ----- Forwarded message from Scott Robert Ladd <coyote at coyotegulch.com> -----
> 
> Date: 	Mon, 24 Nov 2003 12:49:59 -0500
> From: Scott Robert Ladd <coyote at coyotegulch.com>
> To: Linux Kernel Mailing List <linux-kernel at vger.kernel.org>
> Subject: 2.6.0 and Checkpointing
> 
> I've recently run across CHPOX, Checkpointing for Linux 
> (http://www.cluster.kiev.ua/tasks/chpx_eng.html). I was wondering if 
> anyone else could illuminate me further about using this module with 
> 2.6.0? I'll probably try this myself later today, after I get test10 
> running.
> 
> Has any condieration been made for integrating checkpointing directly 
> into the main kernel build? I'm thinking 2.7, not 2.6, of course.




More information about the cgl_discussion mailing list